Sprint Communications Comapny L.p.

Sprint Communication Cômpany L.p.

Justin Alan Martin

Brian John Washburn

Brian Elwood Hayward

Shaun Michael Johnson

Dean Lee Saghier

Gregory J Atchity

Margaret Mary McMahon

Terry L Reeves

Michael R Hartwig

Dustin T Holub

Edward A Mlodzik

Devin Kelley

R Charles Evans

A method of maintaining server performance comprises receiving, at an analysis server, server performance metrics from at least one monitored server, wherein server performance metrics comprise information about processor usage, memory usage, and network activity and comparing the received metrics with a baseline of values that was established for the server performance metrics based on a variance analysis of historical values. The method further comprises determining that the value of at least one server performance metric of the monitored server is consistently above an upper limit of a range of acceptable deviation from the baseline, analyzing historical occurrences of similar departures of server performance metrics from the range of acceptable deviation, and generating an alert indicating that a risk pattern has been identified and suggesting shutting down a locked process on the monitored server in order to return the server performance metrics to values within the range of acceptable deviation.

Method for qualitative analysis of system performance correlation factors

Systems, methods, and computer-readable media are provided for, among other things, generating web server performance metrics from log file information and storing the metrics offline in a centralized database. A collector accesses log file information from a log file for a web server and generates web server performance metrics on a per web page basis. The web server metrics include a number of requests for a web page, error count for the web page, average response time for the web page, total number of bytes transferred for the web page, and a number of times a service level objection for the web page was exceeded. The web server metrics are stored in a centralized database such that the metrics are available for offline web server performance reporting and analysis.

Collection of web server performance metrics to a centralized database for reporting and analysis

A system is provided that monitors a first and second virtual server on a first physical server containing a physical processor, monitors physical processor usage wherein capacity is allocated to a first entitlement comprising a first percentage of the capacity guaranteed to the first virtual server, to a second entitlement comprising a second percentage guaranteed to the second virtual server, and to a third percentage one of unallocated and partially and totally allocated to a virtual server based on need, and wherein the percentages total to one hundred percent. The system monitors usage of a first virtual processor associated with the first virtual server, receives a request for first virtual processor utilization by percentage, determines utilization comprising first virtual processor usage divided by a first allocated processing capacity comprising the first entitlement and a portion of the third percentage currently allocated to the first virtual server, and reports the utilization.

Virtual server resource monitoring and management

A method of modeling and analyzing load across servers in a cloud computing environment. The method comprises analyzing a processor, a memory, and an input/output utilization of each of a plurality of servers, where each server is comprised of at least one logical partition. A chart displaying a usage pattern is presented for each server. A list of logical partitions is presented for each server of the plurality of servers. A selection of at least one logical partition on a first server of the plurality of servers and a selection of a second server of the plurality of servers is received. The utilization impacts of moving the logical partition to the selected second server are modeled and an updated chart displaying the usage pattern for each server based on the modeled migration of the logical partition is presented. The modeled optimal location stored in a disaster recovery plan.

Server maintenance modeling in cloud computing

A system is provided comprising processor, memory, and application that captures production server metrics, and accesses an analytical model modeling response times and system utilization. The system enters a configuration into the model simulating the production environment and comprises a load and growth factor, generates modeled response times, calculates throughput rates, and determines a baseline production load. The system combines throughput rates and response times with the baseline production to project future throughput rates and response times. The system identifies at least one production server load metric associated with at least one of a projected future throughput rate and response time approaching a constant and executes a work order for a hardware or software change in the production environment based on at least one observed production server load metric associated with at the least one of a projected future throughput rate and a projected future response time approaching a constant.

Automated determination of system scalability and scalability constraint factors

A method is provided for garbage collection in a heap of an application server that uses automated garbage collection. The method comprises gathering information about a plurality of garbage collection events. The method further comprises identifying a correlation between garbage collection activity and a volume of applications transactions in the application server. The method further comprises, based on the correlation, forecasting at least one of a future utilization of heap memory and a future garbage collection activity based on a projected future transaction volume. The method further comprises tuning the heap based on the forecast.

Method and system for adaptive recovery of heap memory

A data collection system is provided. The system comprises a central server that stores configuration data, a plurality of data sources that produce data, and a plurality of collectors. Each of the plurality of collectors is stored in a computer readable storage medium and executable by a processor to obtain corresponding configuration data from the central server, compare the obtained configuration data to configuration data stored in memory of a corresponding server, replace at least a portion of the configuration data stored in memory with at least a portion of the obtained configuration data when the obtained configuration data is different than the configuration data stored in memory, and collect data from one of the plurality of data sources based on at least the at least a portion of the obtained configuration data when the obtained configuration data is different than the configuration data stored in memory.

Enhanced data collection techniques

A data collection system is provided. The system comprises a plurality of data sources that produce data. At least some of the plurality of data sources produce data in different formats. The system also comprises a plurality of listeners stored in a computer readable storage medium that, when executed by a processor, receive the data from the plurality of data sources, identify the data, parse the data, convert the data into a generic format, and validate the converted data. The plurality of listeners are implemented using a script programming language. The system further comprises a loader stored in a computer readable storage medium that, when executed by a processor, loads the converted data into a database. The loader is implemented using an object oriented programming language.

A self-selected message queue monitoring system is provided. The system comprises a processor, a memory, and an application stored in the memory that, when executed by the processor, presents an interface to a requester enabling self-registration for selection of monitoring of at least one message queue of a plurality of message queues associated with a plurality of user applications. The system also receives a message completing self-registration for monitoring, the message selecting monitoring of a first message queue associated with a first user application. The system also authorizes the requester to access periodically collected information about the first message queue. The system also determines, at a predetermined time, a first metric associated with the first message queue wherein the first metric is specified in the message completing self-registration, and stores the first metric for access by the requester.

Self-selected message queue monitoring

A system provides network application transaction analysis. An analysis tool, when executed by a processor, measures an application transaction metric and calculates a historical system average and a historical application average associated with the application transaction metric based on server performance logs. The tool determines whether the application transaction metric differs from the historical system average by more than a first threshold amount during consecutive measurements. The tool determines whether the application transaction metric differs from the historical application average by more than a second threshold amount during consecutive measurements if the application transaction metric does not differ from the historical system average by more than the first threshold amount during consecutive measurements. The tool outputs an alarm to a user interface to enable a generation of an investigation if the application transaction metric differs from the historical application average by more than the second threshold amount during consecutive measurements.

Application transaction analysis

The present invention provides a method for modeling the performance of a system comprising computer software operating on computer hardware. In accordance with the present invention, system performance is modeled by fitting non-linear curves to data points for system performance parameters, such as response time and throughput, as a function of load. Data points may be measured in testing may be measured through monitoring a system operating in a production environment. While a variety of non-linear curves may be used in accordance with the present invention, a logarithmic curve may be used to model system throughput and an exponential curve may be used to model system response time. By defining a relationship between throughput and response time a distance may be calculated between the curves, and this distance may be used to determine an optimal load. Additionally, a graph displaying both throughput and response time as a function of load may be displayed to a system operator in a graphical user interface to facilitate the evaluation of system performance.

Growing community of inventors

Olathe, KS, United States of America

Justin Alan Martin